In [2]:
from nussl import jupyter_utils, AudioSignal
In [41]:
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:65% !important; font-size:1em;}</style>"))
In [16]:
from IPython.display import HTML

HTML('''<script>
code_show=true; 
function code_toggle() {
 if (code_show){
 $('div.input').hide();
 } else {
 $('div.input').show();
 }
 code_show = !code_show
} 
$( document ).ready(code_toggle);
</script>
<form action="javascript:code_toggle()"><input type="submit" value="Click here to toggle on/off the raw code."></form>''')
Out[16]:

Figure 1.2

An example of audio representations. The top plot depicts the time-series representation, while the bottom plot depicts the spectrogram (time-frequency) representation. The auditory scene consists of a small jazz band (consisting of saxophone, piano, drums, and bass), chatter produced by a crowd of people, and dishes clattering as they are being washed. It is difficult to visually separate the three sources from each other in either the time-frequency representation or the original time-series.

In [46]:
from wand.image import Image as WImage
img = WImage(filename='../mixture.png')
img
Out[46]:
In [47]:
audio = [
    ('mixture/mix2-261.wav', 'Mixture'),
]
for a, l in audio:
    print(l)
    s = AudioSignal(a)
    s.to_mono()
    jupyter_utils.embed_audio(s, display=True)
Mixture

Figure 1.3

An example of time-frequency assignments in the spectrogram from Figure 1.2. The auditory scene consists of a small jazz band consisting of saxophone, piano, drums, and bass, chatter produced by a crowd of people, and dishes clattering as they are being washed. Dark blue represents silence, light blue represents the jazz band, red the chatter, and yellow the dishes.

In [48]:
from wand.image import Image as WImage
img = WImage(filename='../separated.png')
img
Out[48]:
In [49]:
audio = [
    ('mixture/separated_music-268.wav', 'Separated music (light blue mask)'),
]
for a, l in audio:
    print(l)
    s = AudioSignal(a)
    s.to_mono()
    jupyter_utils.embed_audio(s, display=True)
Separated music (light blue mask)